© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 13717
    Prev
    Next
    INDEX
    Explanations

    environmental topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æ²¹èħ»
    -0.22
     Accessories
    -0.21
     pimp
    -0.20
    éķ§
    -0.20
    èĩªè±ª
    -0.20
    åĬ²
    -0.19
    äºĮ线åŁİå¸Ĥ
    -0.19
    èµı
    -0.19
    æĮ¯ãĤĬ
    -0.19
    èµŀç¾İ
    -0.19
    POSITIVE LOGITS
    ä¿ĿæĬ¤
    0.27
    èĦĨå¼±
    0.26
    åıĹå½±åĵį
    0.26
    å½±åĵį
    0.24
    严éĩįå½±åĵį
    0.24
    ä¿Ŀéļľ
    0.24
    ä¿ĿæĬ¤åĮº
    0.24
    æķıæĦŁ
    0.23
    lover
    0.23
     protection
    0.22
    Activations Density 0.028%

    No Known Activations